scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

Merge pull request #35270 from BerriAI/litellm_gpt_pricing_change

Browse source 
fix(pricing): correct gpt-5.6 prices for openai, bedrock, and flex long context
This commit is contained in:
Mateo Wang 2026-07-30 21:46:46 -07:00 • committed by GitHub
commit bf1a8fe403
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 270 additions and 251 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

104
litellm/model_prices_and_context_window_backup.json
View file

@ -23678,14 +23678,17 @@
"gpt-5.6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_flex": 6.25e-06,
"cache_creation_input_token_cost_flex": 3.125e-06,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
"cache_read_input_token_cost_flex": 2.5e-07,
"cache_read_input_token_cost_priority": 1e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_batches": 2.5e-06,
"input_cost_per_token_flex": 2.5e-06,
"input_cost_per_token_priority": 1e-05,
@ -23696,6 +23699,7 @@
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"output_cost_per_token_batches": 1.5e-05,
"output_cost_per_token_flex": 1.5e-05,
"output_cost_per_token_priority": 6e-05,
@ -23731,14 +23735,17 @@
"gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_flex": 6.25e-06,
"cache_creation_input_token_cost_flex": 3.125e-06,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
"cache_read_input_token_cost_flex": 2.5e-07,
"cache_read_input_token_cost_priority": 1e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_batches": 2.5e-06,
"input_cost_per_token_flex": 2.5e-06,
"input_cost_per_token_priority": 1e-05,
@ -23749,6 +23756,7 @@
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"output_cost_per_token_batches": 1.5e-05,
"output_cost_per_token_flex": 1.5e-05,
"output_cost_per_token_priority": 6e-05,
@ -23782,29 +23790,33 @@
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-terra": {
"cache_creation_input_token_cost": 3.125e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6.25e-06,
"cache_creation_input_token_cost_flex": 1.5625e-06,
"cache_creation_input_token_cost_priority": 6.25e-06,
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_flex": 1.25e-07,
"cache_read_input_token_cost_priority": 5e-07,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_batches": 1.25e-06,
"input_cost_per_token_flex": 1.25e-06,
"input_cost_per_token_priority": 5e-06,
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06,
"cache_creation_input_token_cost_flex": 1.25e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 2e-07,
"cache_read_input_token_cost_flex": 1e-07,
"cache_read_input_token_cost_priority": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_flex": 2e-06,
"input_cost_per_token_batches": 1e-06,
"input_cost_per_token_flex": 1e-06,
"input_cost_per_token_priority": 4e-06,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_batches": 7.5e-06,
"output_cost_per_token_flex": 7.5e-06,
"output_cost_per_token_priority": 3e-05,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"output_cost_per_token_above_272k_tokens_flex": 9e-06,
"output_cost_per_token_batches": 6e-06,
"output_cost_per_token_flex": 6e-06,
"output_cost_per_token_priority": 2.4e-05,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
@ -23835,29 +23847,33 @@
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-luna": {
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
"cache_creation_input_token_cost_flex": 6.25e-07,
"cache_creation_input_token_cost_priority": 2.5e-06,
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2e-07,
"cache_read_input_token_cost_flex": 5e-08,
"cache_read_input_token_cost_priority": 2e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"input_cost_per_token_batches": 5e-07,
"input_cost_per_token_flex": 5e-07,
"input_cost_per_token_priority": 2e-06,
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07,
"cache_creation_input_token_cost_flex": 1.25e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_above_272k_tokens_flex": 2e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_priority": 4e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_above_272k_tokens_flex": 2e-07,
"input_cost_per_token_batches": 1e-07,
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_priority": 4e-07,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_272k_tokens": 9e-06,
"output_cost_per_token_batches": 3e-06,
"output_cost_per_token_flex": 3e-06,
"output_cost_per_token_priority": 1.2e-05,
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_above_272k_tokens_flex": 9e-07,
"output_cost_per_token_batches": 6e-07,
"output_cost_per_token_flex": 6e-07,
"output_cost_per_token_priority": 2.4e-06,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
@ -45120,10 +45136,10 @@
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.6-terra": {
"input_cost_per_token": 2.75e-06,
"cache_creation_input_token_cost": 3.4375e-06,
"cache_read_input_token_cost": 2.75e-07,
"output_cost_per_token": 1.65e-05,
"input_cost_per_token": 2.2e-06,
"cache_creation_input_token_cost": 2.75e-06,
"cache_read_input_token_cost": 2.2e-07,
"output_cost_per_token": 1.32e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
@ -45148,10 +45164,10 @@
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.6-luna": {
"input_cost_per_token": 1.1e-06,
"cache_creation_input_token_cost": 1.375e-06,
"cache_read_input_token_cost": 1.1e-07,
"output_cost_per_token": 6.6e-06,
"input_cost_per_token": 2.2e-07,
"cache_creation_input_token_cost": 2.75e-07,
"cache_read_input_token_cost": 2.2e-08,
"output_cost_per_token": 1.32e-06,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,

16
litellm/types/utils.py
View file

@ -200,7 +200,12 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_token_priority: Optional[float] # OpenAI priority service tier pricing
cache_creation_input_token_cost: Optional[float]
cache_creation_input_token_cost_above_200k_tokens: Optional[float]
cache_creation_input_token_cost_above_272k_tokens: Optional[float]
cache_creation_input_token_cost_above_272k_tokens_priority: Optional[float]
cache_creation_input_token_cost_above_272k_tokens_flex: Optional[float]
cache_creation_input_token_cost_above_1hr: Optional[float]
cache_creation_input_token_cost_flex: Optional[float] # OpenAI flex service tier pricing
cache_creation_input_token_cost_priority: Optional[float] # OpenAI priority service tier pricing
cache_read_input_token_cost: Optional[float]
cache_read_input_token_cost_flex: Optional[float] # OpenAI flex service tier pricing
cache_read_input_token_cost_priority: Optional[float] # OpenAI priority service tier pricing
@ -208,6 +213,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
cache_read_input_token_cost_above_200k_tokens_priority: Optional[float]
cache_read_input_token_cost_above_272k_tokens: Optional[float]
cache_read_input_token_cost_above_272k_tokens_priority: Optional[float]
cache_read_input_token_cost_above_272k_tokens_flex: Optional[float]
cache_read_input_token_cost_above_512k_tokens: Optional[float]
# Smallest prefix this model will actually cache, whatever caching mechanism its provider uses.
# Absent means the provider-agnostic default applies; see MINIMUM_PROMPT_CACHE_TOKEN_COUNT.
@ -219,6 +225,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_token_above_200k_tokens_priority: Optional[float]
input_cost_per_token_above_272k_tokens: Optional[float] # GPT-5.4/5.4-pro: prompts >272K priced at 2x input
input_cost_per_token_above_272k_tokens_priority: Optional[float]
input_cost_per_token_above_272k_tokens_flex: Optional[float]
input_cost_per_token_above_512k_tokens: Optional[float] # MiniMax-M3: prompts >512K priced at 2x input
input_cost_per_character_above_128k_tokens: Optional[float] # only for vertex ai models
input_cost_per_query: Optional[float] # only for rerank models
@ -246,6 +253,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
output_cost_per_token_above_200k_tokens_priority: Optional[float]
output_cost_per_token_above_272k_tokens: Optional[float] # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output
output_cost_per_token_above_272k_tokens_priority: Optional[float]
output_cost_per_token_above_272k_tokens_flex: Optional[float]
output_cost_per_token_above_512k_tokens: Optional[float] # MiniMax-M3: prompts >512K priced at 2x output
output_cost_per_character_above_128k_tokens: Optional[float] # only for vertex ai models
output_cost_per_image: Optional[float]
@ -3165,6 +3173,11 @@ class CustomPricingLiteLLMParams(BaseModel):
cache_creation_input_token_cost: Optional[float] = None
cache_creation_input_token_cost_above_1hr: Optional[float] = None
cache_creation_input_token_cost_above_200k_tokens: Optional[float] = None
cache_creation_input_token_cost_above_272k_tokens: Optional[float] = None
cache_creation_input_token_cost_above_272k_tokens_priority: Optional[float] = None
cache_creation_input_token_cost_above_272k_tokens_flex: Optional[float] = None
cache_creation_input_token_cost_flex: Optional[float] = None
cache_creation_input_token_cost_priority: Optional[float] = None
cache_creation_input_audio_token_cost: Optional[float] = None
cache_read_input_token_cost: Optional[float] = None
cache_read_input_token_cost_flex: Optional[float] = None
@ -3172,6 +3185,7 @@ class CustomPricingLiteLLMParams(BaseModel):
cache_read_input_token_cost_above_200k_tokens: Optional[float] = None
cache_read_input_token_cost_above_200k_tokens_priority: Optional[float] = None
cache_read_input_token_cost_above_272k_tokens_priority: Optional[float] = None
cache_read_input_token_cost_above_272k_tokens_flex: Optional[float] = None
cache_read_input_audio_token_cost: Optional[float] = None
input_cost_per_character: Optional[float] = None
input_cost_per_character_above_128k_tokens: Optional[float] = None
@ -3181,6 +3195,7 @@ class CustomPricingLiteLLMParams(BaseModel):
input_cost_per_token_above_200k_tokens: Optional[float] = None
input_cost_per_token_above_200k_tokens_priority: Optional[float] = None
input_cost_per_token_above_272k_tokens_priority: Optional[float] = None
input_cost_per_token_above_272k_tokens_flex: Optional[float] = None
input_cost_per_query: Optional[float] = None
input_cost_per_image: Optional[float] = None
input_cost_per_image_above_128k_tokens: Optional[float] = None
@ -3200,6 +3215,7 @@ class CustomPricingLiteLLMParams(BaseModel):
output_cost_per_token_above_200k_tokens: Optional[float] = None
output_cost_per_token_above_200k_tokens_priority: Optional[float] = None
output_cost_per_token_above_272k_tokens_priority: Optional[float] = None
output_cost_per_token_above_272k_tokens_flex: Optional[float] = None
output_cost_per_character_above_128k_tokens: Optional[float] = None
output_cost_per_image: Optional[float] = None
output_cost_per_image_token: Optional[float] = None

22
litellm/utils.py
View file

@ -5410,6 +5410,19 @@ def _get_model_info_helper(
cache_creation_input_token_cost_above_200k_tokens=_model_info.get(
"cache_creation_input_token_cost_above_200k_tokens", None
),
cache_creation_input_token_cost_above_272k_tokens=_model_info.get(
"cache_creation_input_token_cost_above_272k_tokens", None
),
cache_creation_input_token_cost_above_272k_tokens_priority=_model_info.get(
"cache_creation_input_token_cost_above_272k_tokens_priority", None
),
cache_creation_input_token_cost_above_272k_tokens_flex=_model_info.get(
"cache_creation_input_token_cost_above_272k_tokens_flex", None
),
cache_creation_input_token_cost_flex=_model_info.get("cache_creation_input_token_cost_flex", None),
cache_creation_input_token_cost_priority=_model_info.get(
"cache_creation_input_token_cost_priority", None
),
cache_read_input_token_cost=_model_info.get("cache_read_input_token_cost", None),
prompt_cache_min_tokens=_model_info.get("prompt_cache_min_tokens", None),
cache_read_input_token_cost_above_200k_tokens=_model_info.get(
@ -5424,6 +5437,9 @@ def _get_model_info_helper(
cache_read_input_token_cost_above_272k_tokens_priority=_model_info.get(
"cache_read_input_token_cost_above_272k_tokens_priority", None
),
cache_read_input_token_cost_above_272k_tokens_flex=_model_info.get(
"cache_read_input_token_cost_above_272k_tokens_flex", None
),
cache_read_input_token_cost_above_512k_tokens=_model_info.get(
"cache_read_input_token_cost_above_512k_tokens", None
),
@ -5442,6 +5458,9 @@ def _get_model_info_helper(
input_cost_per_token_above_272k_tokens_priority=_model_info.get(
"input_cost_per_token_above_272k_tokens_priority", None
),
input_cost_per_token_above_272k_tokens_flex=_model_info.get(
"input_cost_per_token_above_272k_tokens_flex", None
),
input_cost_per_token_above_512k_tokens=_model_info.get("input_cost_per_token_above_512k_tokens", None),
input_cost_per_query=_model_info.get("input_cost_per_query", None),
input_cost_per_second=_model_info.get("input_cost_per_second", None),
@ -5483,6 +5502,9 @@ def _get_model_info_helper(
output_cost_per_token_above_272k_tokens_priority=_model_info.get(
"output_cost_per_token_above_272k_tokens_priority", None
),
output_cost_per_token_above_272k_tokens_flex=_model_info.get(
"output_cost_per_token_above_272k_tokens_flex", None
),
output_cost_per_token_above_512k_tokens=_model_info.get(
"output_cost_per_token_above_512k_tokens", None
),

104
model_prices_and_context_window.json
View file

@ -23753,14 +23753,17 @@
"gpt-5.6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_flex": 6.25e-06,
"cache_creation_input_token_cost_flex": 3.125e-06,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
"cache_read_input_token_cost_flex": 2.5e-07,
"cache_read_input_token_cost_priority": 1e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_batches": 2.5e-06,
"input_cost_per_token_flex": 2.5e-06,
"input_cost_per_token_priority": 1e-05,
@ -23771,6 +23774,7 @@
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"output_cost_per_token_batches": 1.5e-05,
"output_cost_per_token_flex": 1.5e-05,
"output_cost_per_token_priority": 6e-05,
@ -23806,14 +23810,17 @@
"gpt-5.6-sol": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens_flex": 6.25e-06,
"cache_creation_input_token_cost_flex": 3.125e-06,
"cache_creation_input_token_cost_priority": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
"cache_read_input_token_cost_flex": 2.5e-07,
"cache_read_input_token_cost_priority": 1e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"input_cost_per_token_batches": 2.5e-06,
"input_cost_per_token_flex": 2.5e-06,
"input_cost_per_token_priority": 1e-05,
@ -23824,6 +23831,7 @@
"mode": "chat",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"output_cost_per_token_batches": 1.5e-05,
"output_cost_per_token_flex": 1.5e-05,
"output_cost_per_token_priority": 6e-05,
@ -23857,29 +23865,33 @@
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-terra": {
"cache_creation_input_token_cost": 3.125e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6.25e-06,
"cache_creation_input_token_cost_flex": 1.5625e-06,
"cache_creation_input_token_cost_priority": 6.25e-06,
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_flex": 1.25e-07,
"cache_read_input_token_cost_priority": 5e-07,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_batches": 1.25e-06,
"input_cost_per_token_flex": 1.25e-06,
"input_cost_per_token_priority": 5e-06,
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06,
"cache_creation_input_token_cost_flex": 1.25e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 2e-07,
"cache_read_input_token_cost_flex": 1e-07,
"cache_read_input_token_cost_priority": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_flex": 2e-06,
"input_cost_per_token_batches": 1e-06,
"input_cost_per_token_flex": 1e-06,
"input_cost_per_token_priority": 4e-06,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_batches": 7.5e-06,
"output_cost_per_token_flex": 7.5e-06,
"output_cost_per_token_priority": 3e-05,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"output_cost_per_token_above_272k_tokens_flex": 9e-06,
"output_cost_per_token_batches": 6e-06,
"output_cost_per_token_flex": 6e-06,
"output_cost_per_token_priority": 2.4e-05,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
@ -23910,29 +23922,33 @@
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-luna": {
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
"cache_creation_input_token_cost_flex": 6.25e-07,
"cache_creation_input_token_cost_priority": 2.5e-06,
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2e-07,
"cache_read_input_token_cost_flex": 5e-08,
"cache_read_input_token_cost_priority": 2e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"input_cost_per_token_batches": 5e-07,
"input_cost_per_token_flex": 5e-07,
"input_cost_per_token_priority": 2e-06,
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07,
"cache_creation_input_token_cost_flex": 1.25e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_above_272k_tokens_flex": 2e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_priority": 4e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_above_272k_tokens_flex": 2e-07,
"input_cost_per_token_batches": 1e-07,
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_priority": 4e-07,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_272k_tokens": 9e-06,
"output_cost_per_token_batches": 3e-06,
"output_cost_per_token_flex": 3e-06,
"output_cost_per_token_priority": 1.2e-05,
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_above_272k_tokens_flex": 9e-07,
"output_cost_per_token_batches": 6e-07,
"output_cost_per_token_flex": 6e-07,
"output_cost_per_token_priority": 2.4e-06,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
@ -45241,10 +45257,10 @@
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.6-terra": {
"input_cost_per_token": 2.75e-06,
"cache_creation_input_token_cost": 3.4375e-06,
"cache_read_input_token_cost": 2.75e-07,
"output_cost_per_token": 1.65e-05,
"input_cost_per_token": 2.2e-06,
"cache_creation_input_token_cost": 2.75e-06,
"cache_read_input_token_cost": 2.2e-07,
"output_cost_per_token": 1.32e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
@ -45269,10 +45285,10 @@
"supports_vision": true
},
"bedrock_mantle/openai.gpt-5.6-luna": {
"input_cost_per_token": 1.1e-06,
"cache_creation_input_token_cost": 1.375e-06,
"cache_read_input_token_cost": 1.1e-07,
"output_cost_per_token": 6.6e-06,
"input_cost_per_token": 2.2e-07,
"cache_creation_input_token_cost": 2.75e-07,
"cache_read_input_token_cost": 2.2e-08,
"output_cost_per_token": 1.32e-06,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 272000,
"max_output_tokens": 128000,

20
model_prices_and_context_window.schema.json
View file

@ -99,6 +99,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_creation_input_token_cost_above_272k_tokens_flex": {
"type": "number",
"minimum": 0,
"description": "Flex service-tier rate for the same-named base field."
},
"cache_creation_input_token_cost_flex": {
"type": "number",
"minimum": 0,
@ -133,6 +138,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_read_input_token_cost_above_272k_tokens_flex": {
"type": "number",
"minimum": 0,
"description": "Flex service-tier rate for the same-named base field."
},
"cache_read_input_token_cost_above_272k_tokens_priority": {
"type": "number",
"minimum": 0,
@ -262,6 +272,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"input_cost_per_token_above_272k_tokens_flex": {
"type": "number",
"minimum": 0,
"description": "Flex service-tier rate for the same-named base field."
},
"input_cost_per_token_above_272k_tokens_priority": {
"type": "number",
"minimum": 0,
@ -434,6 +449,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"output_cost_per_token_above_272k_tokens_flex": {
"type": "number",
"minimum": 0,
"description": "Flex service-tier rate for the same-named base field."
},
"output_cost_per_token_above_272k_tokens_priority": {
"type": "number",
"minimum": 0,

52
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -611,8 +611,8 @@ def test_generic_cost_per_token_gpt55_pro():
[
("gpt-5.6", 5e-6, 3e-5, 5e-7, 6.25e-6),
("gpt-5.6-sol", 5e-6, 3e-5, 5e-7, 6.25e-6),
("gpt-5.6-terra", 2.5e-6, 1.5e-5, 2.5e-7, 3.125e-6),
("gpt-5.6-luna", 1e-6, 6e-6, 1e-7, 1.25e-6),
("gpt-5.6-terra", 2e-6, 1.2e-5, 2e-7, 2.5e-6),
("gpt-5.6-luna", 2e-7, 1.2e-6, 2e-8, 2.5e-7),
],
)
def test_generic_cost_per_token_gpt56(
@ -661,6 +661,54 @@ def test_generic_cost_per_token_gpt56(
assert round(completion_cost, 10) == round(output_cost * completion_tokens, 10)
@pytest.mark.parametrize(
"model,flex_long_input_cost,flex_long_output_cost",
[
("gpt-5.6", 5e-6, 2.25e-5),
("gpt-5.6-sol", 5e-6, 2.25e-5),
("gpt-5.6-terra", 2e-6, 9e-6),
("gpt-5.6-luna", 2e-7, 9e-7),
],
)
def test_generic_cost_per_token_gpt56_flex_above_272k(
model, flex_long_input_cost, flex_long_output_cost
):
"""A >272K flex request bills the flex long-context rate, not the standard one.
Flex long-context is half the standard long-context rate. Without the
``*_above_272k_tokens_flex`` keys these requests silently fell back to the
standard long-context price, billing 2x what OpenAI charges.
"""
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
prompt_tokens = 300000
completion_tokens = 1000
usage = Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
)
prompt_cost, completion_cost = generic_cost_per_token(
model=model,
usage=usage,
custom_llm_provider="openai",
service_tier="flex",
)
assert prompt_cost == pytest.approx(flex_long_input_cost * prompt_tokens)
assert completion_cost == pytest.approx(flex_long_output_cost * completion_tokens)
standard_long_prompt_cost, standard_long_completion_cost = generic_cost_per_token(
model=model,
usage=usage,
custom_llm_provider="openai",
service_tier=None,
)
assert prompt_cost == pytest.approx(standard_long_prompt_cost / 2)
assert completion_cost == pytest.approx(standard_long_completion_cost / 2)
@pytest.mark.parametrize(
"model,input_cost,output_cost,cache_read_cost",
[

4
tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py
View file

@ -1519,8 +1519,8 @@ class TestBedrockMantleResponsesPricing:
"model, input_cost, cache_creation_cost, cache_read_cost, output_cost",
[
("openai.gpt-5.6-sol", 5.5e-06, 6.875e-06, 5.5e-07, 3.3e-05),
("openai.gpt-5.6-terra", 2.75e-06, 3.4375e-06, 2.75e-07, 1.65e-05),
("openai.gpt-5.6-luna", 1.1e-06, 1.375e-06, 1.1e-07, 6.6e-06),
("openai.gpt-5.6-terra", 2.2e-06, 2.75e-06, 2.2e-07, 1.32e-05),
("openai.gpt-5.6-luna", 2.2e-07, 2.75e-07, 2.2e-08, 1.32e-06),
],
)
def test_gpt_5_6_pricing_and_mode(

159
tests/test_litellm/test_gpt_5_6_model_metadata.py
View file

@ -1,159 +0,0 @@
import json
from pathlib import Path
import pytest
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
GPT_5_6_MODELS = ("gpt-5.6", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna")
STANDARD_PRICING = {
"gpt-5.6": (5e-06, 3e-05, 5e-07, 6.25e-06),
"gpt-5.6-sol": (5e-06, 3e-05, 5e-07, 6.25e-06),
"gpt-5.6-terra": (2.5e-06, 1.5e-05, 2.5e-07, 3.125e-06),
"gpt-5.6-luna": (1e-06, 6e-06, 1e-07, 1.25e-06),
}
@pytest.mark.parametrize("model", GPT_5_6_MODELS)
def test_openai_gpt_5_6_model_info(model):
json_path = Path(__file__).parents[2] / "model_prices_and_context_window.json"
with open(json_path) as f:
model_cost = json.load(f)
info = model_cost.get(model)
assert info is not None, f"{model} not found in model_prices_and_context_window.json"
assert info["litellm_provider"] == "openai"
assert info["mode"] == "chat"
input_cost, output_cost, cache_read_cost, cache_write_cost = STANDARD_PRICING[model]
assert info["input_cost_per_token"] == input_cost
assert info["output_cost_per_token"] == output_cost
assert info["cache_read_input_token_cost"] == cache_read_cost
assert info["cache_creation_input_token_cost"] == cache_write_cost
assert info["cache_creation_input_token_cost"] == pytest.approx(input_cost * 1.25)
assert info["input_cost_per_token_above_272k_tokens"] == pytest.approx(input_cost * 2)
assert info["output_cost_per_token_above_272k_tokens"] == pytest.approx(output_cost * 1.5)
assert info["cache_read_input_token_cost_above_272k_tokens"] == pytest.approx(cache_read_cost * 2)
assert info["max_input_tokens"] == 1050000
assert info["max_output_tokens"] == 128000
assert info["max_tokens"] == 128000
assert info["supports_function_calling"] is True
assert info["supports_prompt_caching"] is True
assert info["supports_reasoning"] is True
assert info["supports_response_schema"] is True
assert info["supports_tool_choice"] is True
assert info["supports_vision"] is True
assert info["supports_web_search"] is True
assert info["supports_none_reasoning_effort"] is True
assert info["supports_xhigh_reasoning_effort"] is True
assert info["supports_minimal_reasoning_effort"] is False
assert info["supported_endpoints"] == ["/v1/chat/completions", "/v1/batch", "/v1/responses"]
assert info["supported_modalities"] == ["text", "image"]
assert info["supported_output_modalities"] == ["text"]
routed_model, provider, _, _ = get_llm_provider(model=f"openai/{model}")
assert routed_model == model
assert provider == "openai"
AZURE_GLOBAL_MODELS = (
"azure/gpt-5.6",
"azure/gpt-5.6-sol",
"azure/gpt-5.6-terra",
"azure/gpt-5.6-luna",
)
AZURE_REGIONAL_MODELS = tuple(
f"azure/{region}/{tier}"
for region in ("us", "eu")
for tier in ("gpt-5.6", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna")
)
def _tier_key(azure_model):
return azure_model.split("/")[-1]
def _load_main():
json_path = Path(__file__).parents[2] / "model_prices_and_context_window.json"
with open(json_path) as f:
return json.load(f)
@pytest.mark.parametrize("model", AZURE_GLOBAL_MODELS)
def test_azure_gpt_5_6_global_model_info(model):
model_cost = _load_main()
info = model_cost.get(model)
assert info is not None, f"{model} not found in model_prices_and_context_window.json"
assert info["litellm_provider"] == "azure"
assert info["mode"] == "chat"
input_cost, output_cost, cache_read_cost, _ = STANDARD_PRICING[_tier_key(model)]
assert info["input_cost_per_token"] == input_cost
assert info["output_cost_per_token"] == output_cost
assert info["cache_read_input_token_cost"] == cache_read_cost
assert info["input_cost_per_token_above_272k_tokens"] == pytest.approx(input_cost * 2)
assert info["output_cost_per_token_above_272k_tokens"] == pytest.approx(output_cost * 1.5)
assert info["input_cost_per_token_priority"] == pytest.approx(input_cost * 2)
assert info["output_cost_per_token_priority"] == pytest.approx(output_cost * 2)
assert info["input_cost_per_token_above_272k_tokens_priority"] == pytest.approx(input_cost * 4)
assert info["output_cost_per_token_above_272k_tokens_priority"] == pytest.approx(output_cost * 3)
assert info["max_input_tokens"] == 1050000
assert info["max_output_tokens"] == 128000
assert info["supports_reasoning"] is True
routed_model, provider, _, _ = get_llm_provider(model=model)
assert provider == "azure"
@pytest.mark.parametrize("model", AZURE_REGIONAL_MODELS)
def test_azure_gpt_5_6_regional_model_info(model):
model_cost = _load_main()
info = model_cost.get(model)
assert info is not None, f"{model} not found in model_prices_and_context_window.json"
assert info["litellm_provider"] == "azure"
assert info["mode"] == "chat"
input_cost, output_cost, cache_read_cost, _ = STANDARD_PRICING[_tier_key(model)]
assert info["input_cost_per_token"] == pytest.approx(input_cost * 1.1)
assert info["output_cost_per_token"] == pytest.approx(output_cost * 1.1)
assert info["cache_read_input_token_cost"] == pytest.approx(cache_read_cost * 1.1)
assert info["input_cost_per_token_above_272k_tokens"] == pytest.approx(input_cost * 2.2)
assert info["output_cost_per_token_above_272k_tokens"] == pytest.approx(output_cost * 1.65)
assert info["input_cost_per_token_priority"] == pytest.approx(input_cost * 2.75)
assert info["output_cost_per_token_priority"] == pytest.approx(output_cost * 2.75)
assert info["max_input_tokens"] == 1050000
assert info["max_output_tokens"] == 128000
assert info["supports_reasoning"] is True
_, provider, _, _ = get_llm_provider(model=model)
assert provider == "azure"
def test_gpt_5_6_backup_matches_main():
"""Ensure the bundled model cost map stays in sync with the canonical file."""
repo_root = Path(__file__).parents[2]
main_path = repo_root / "model_prices_and_context_window.json"
backup_path = repo_root / "litellm" / "model_prices_and_context_window_backup.json"
with open(main_path) as f:
main_cost = json.load(f)
with open(backup_path) as f:
backup_cost = json.load(f)
for model in GPT_5_6_MODELS + AZURE_GLOBAL_MODELS + AZURE_REGIONAL_MODELS:
assert backup_cost.get(model) == main_cost.get(model), (
f"{model} differs between main and backup model cost maps"
)

8
tests/test_litellm/test_utils.py
View file

@ -768,11 +768,17 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"cache_creation_input_token_cost_above_1hr": {"type": "number"},
"cache_creation_input_token_cost_above_200k_tokens": {"type": "number"},
"cache_creation_input_token_cost_above_272k_tokens": {"type": "number"},
"cache_creation_input_token_cost_above_272k_tokens_flex": {
"type": "number"
},
"cache_creation_input_token_cost_flex": {"type": "number"},
"cache_creation_input_token_cost_priority": {"type": "number"},
"cache_read_input_token_cost": {"type": "number"},
"cache_read_input_token_cost_above_200k_tokens": {"type": "number"},
"cache_read_input_token_cost_above_272k_tokens": {"type": "number"},
"cache_read_input_token_cost_above_272k_tokens_flex": {
"type": "number"
},
"cache_read_input_token_cost_above_512k_tokens": {"type": "number"},
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": {
"type": "number"
@ -806,11 +812,13 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"input_cost_per_token_priority": {"type": "number"},
"input_cost_per_token_above_200k_tokens_priority": {"type": "number"},
"input_cost_per_token_above_272k_tokens_priority": {"type": "number"},
"input_cost_per_token_above_272k_tokens_flex": {"type": "number"},
"input_cost_per_audio_token_priority": {"type": "number"},
"output_cost_per_token_flex": {"type": "number"},
"output_cost_per_token_priority": {"type": "number"},
"output_cost_per_token_above_200k_tokens_priority": {"type": "number"},
"output_cost_per_token_above_272k_tokens_priority": {"type": "number"},
"output_cost_per_token_above_272k_tokens_flex": {"type": "number"},
"regional_processing_uplift_multiplier_eu": {"type": "number"},
"regional_processing_uplift_multiplier_us": {"type": "number"},
"input_cost_per_pixel": {"type": "number"},

32
ui/litellm-dashboard/src/lib/http/schema.d.ts generated vendored
View file

@ -25849,6 +25849,16 @@ export interface components {
cache_creation_input_token_cost_above_1hr?: number | null;
/** Cache Creation Input Token Cost Above 200K Tokens */
cache_creation_input_token_cost_above_200k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 272K Tokens */
cache_creation_input_token_cost_above_272k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 272K Tokens Flex */
cache_creation_input_token_cost_above_272k_tokens_flex?: number | null;
/** Cache Creation Input Token Cost Above 272K Tokens Priority */
cache_creation_input_token_cost_above_272k_tokens_priority?: number | null;
/** Cache Creation Input Token Cost Flex */
cache_creation_input_token_cost_flex?: number | null;
/** Cache Creation Input Token Cost Priority */
cache_creation_input_token_cost_priority?: number | null;
/** Cache Read Input Audio Token Cost */
cache_read_input_audio_token_cost?: number | null;
/** Cache Read Input Token Cost */
@ -25859,6 +25869,8 @@ export interface components {
cache_read_input_token_cost_above_200k_tokens_priority?: number | null;
/** Cache Read Input Token Cost Above 272K Tokens */
cache_read_input_token_cost_above_272k_tokens?: number | null;
/** Cache Read Input Token Cost Above 272K Tokens Flex */
cache_read_input_token_cost_above_272k_tokens_flex?: number | null;
/** Cache Read Input Token Cost Above 272K Tokens Priority */
cache_read_input_token_cost_above_272k_tokens_priority?: number | null;
/** Cache Read Input Token Cost Above 512K Tokens */
@ -25917,6 +25929,8 @@ export interface components {
input_cost_per_token_above_200k_tokens_priority?: number | null;
/** Input Cost Per Token Above 272K Tokens */
input_cost_per_token_above_272k_tokens?: number | null;
/** Input Cost Per Token Above 272K Tokens Flex */
input_cost_per_token_above_272k_tokens_flex?: number | null;
/** Input Cost Per Token Above 272K Tokens Priority */
input_cost_per_token_above_272k_tokens_priority?: number | null;
/** Input Cost Per Token Above 512K Tokens */
@ -26008,6 +26022,8 @@ export interface components {
output_cost_per_token_above_200k_tokens_priority?: number | null;
/** Output Cost Per Token Above 272K Tokens */
output_cost_per_token_above_272k_tokens?: number | null;
/** Output Cost Per Token Above 272K Tokens Flex */
output_cost_per_token_above_272k_tokens_flex?: number | null;
/** Output Cost Per Token Above 272K Tokens Priority */
output_cost_per_token_above_272k_tokens_priority?: number | null;
/** Output Cost Per Token Above 512K Tokens */
@ -33965,6 +33981,16 @@ export interface components {
cache_creation_input_token_cost_above_1hr?: number | null;
/** Cache Creation Input Token Cost Above 200K Tokens */
cache_creation_input_token_cost_above_200k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 272K Tokens */
cache_creation_input_token_cost_above_272k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 272K Tokens Flex */
cache_creation_input_token_cost_above_272k_tokens_flex?: number | null;
/** Cache Creation Input Token Cost Above 272K Tokens Priority */
cache_creation_input_token_cost_above_272k_tokens_priority?: number | null;
/** Cache Creation Input Token Cost Flex */
cache_creation_input_token_cost_flex?: number | null;
/** Cache Creation Input Token Cost Priority */
cache_creation_input_token_cost_priority?: number | null;
/** Cache Read Input Audio Token Cost */
cache_read_input_audio_token_cost?: number | null;
/** Cache Read Input Token Cost */
@ -33975,6 +34001,8 @@ export interface components {
cache_read_input_token_cost_above_200k_tokens_priority?: number | null;
/** Cache Read Input Token Cost Above 272K Tokens */
cache_read_input_token_cost_above_272k_tokens?: number | null;
/** Cache Read Input Token Cost Above 272K Tokens Flex */
cache_read_input_token_cost_above_272k_tokens_flex?: number | null;
/** Cache Read Input Token Cost Above 272K Tokens Priority */
cache_read_input_token_cost_above_272k_tokens_priority?: number | null;
/** Cache Read Input Token Cost Above 512K Tokens */
@ -34033,6 +34061,8 @@ export interface components {
input_cost_per_token_above_200k_tokens_priority?: number | null;
/** Input Cost Per Token Above 272K Tokens */
input_cost_per_token_above_272k_tokens?: number | null;
/** Input Cost Per Token Above 272K Tokens Flex */
input_cost_per_token_above_272k_tokens_flex?: number | null;
/** Input Cost Per Token Above 272K Tokens Priority */
input_cost_per_token_above_272k_tokens_priority?: number | null;
/** Input Cost Per Token Above 512K Tokens */
@ -34124,6 +34154,8 @@ export interface components {
output_cost_per_token_above_200k_tokens_priority?: number | null;
/** Output Cost Per Token Above 272K Tokens */
output_cost_per_token_above_272k_tokens?: number | null;
/** Output Cost Per Token Above 272K Tokens Flex */
output_cost_per_token_above_272k_tokens_flex?: number | null;
/** Output Cost Per Token Above 272K Tokens Priority */
output_cost_per_token_above_272k_tokens_priority?: number | null;
/** Output Cost Per Token Above 512K Tokens */